[Insight-users] itk::PDEDeformableRegistrationFilter InvertOu tput() switch?

Charl P. Botha cpbotha at gmail.com
Mon Dec 6 19:04:25 EST 2004


Hi there James,

Thanks for a fast answer.

On Mon, 6 Dec 2004 18:50:51 -0500, Gee, James <geejames at uphs.upenn.edu> wrote:
> the simplest and most common thing to do is to switch the images you specify
> as fixed and moving.  it's difficult to additionally provide the inverse
> field within the filters because these registrations do not guarantee the
> existence of an inverse, although you could approximate one.  

I've been switching the filters up to now, but for example the Demons
is sensitive to switched inputs (judging by the math in Thirion's
paper and the fact that ITK also has a SymmetricForcesDemons; the
output is not too different though for the data that I have however).

Are you sure it's a real inverse that's required in this case?  For
optical flow, it would really just be the flipped vectors and not a
real inverse.  In this case, adding the flag would mean inverting the
signs of the components when storing each vector.

So my question still remains: if it's as easy as flipping the vectors,
is this a possibility?

Thanks,
Charl


>  
> 
> > -----Original Message----- 
> > From: Charl P. Botha [mailto:cpbotha at gmail.com] 
> > Sent: Monday, December 06, 2004 6:41 PM 
> > To: ITK Users 
> > Subject: [Insight-users] itk::PDEDeformableRegistrationFilter 
> > InvertOutput() switch? 
> > 
> > Dear ITK-ers, 
> > 
> > As far as I can figure out, PDEDeformableRegistrationFilter 
> > descendants (e.g. DemonsRegistrationFilter) return 
> > deformation fields that are directed opposite to the optical 
> > flow from moving image to fixed image.  In other words, the 
> > deformation field is used in the WarpImage class to calculate 
> > for every output position what the corresponding input 
> > position is.  (Please correct me on this if I have missed 
> > something somewhere...) 
> > 
> > In some cases, one would prefer having the optical flow 
> > direction, when for instance using the derived deformation 
> > field to visualise advection.  Would it be possible to have a 
> > switch to reverse the sense of the output deformation field 
> > to be in line with the optical flow expectation?  (this would 
> > simply mean outputting flipped vectors) 
> > 
> > Thanks for any ideas on this, 
> > Charl 
> > 
> > -- 
> > charl p. botha http://cpbotha.net/ 
> > http://visualisation.tudelft.nl/ 
> > _______________________________________________ 
> > Insight-users mailing list 
> > Insight-users at itk.org 
> > http://www.itk.org/mailman/listinfo/insight-users 
> > 


-- 
charl p. botha http://cpbotha.net/ http://visualisation.tudelft.nl/


More information about the Insight-users mailing list